Hanno Labs' small calibrated decision model. A LoRA on Qwen3-1.7B plus trained decision-token embeddings with stable slots, returning the full distribution over up to 255 caller-defined choices and a null slot for Choice, Score and Noul questions.
Upstage's structured decision model, a System One endpoint on Solar Mini 4. Returns a choice, a score or a yes/no answer with a probability read from the model, in one forward pass, on the same /v1/systemone schema as Jev.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
bosun
solar
Fine-tuned from
qwen/qwen3-1.7b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Upstage
Input price
—
$0.10/MTok
Decision accuracy
84.9%
—
Calibration error
0.050
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Evaluation suite
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between bosun and solar-decide?
bosun is from Hanno Labs and solar-decide from Upstage. bosun has open weights you can download and run; solar-decide is only available as a hosted API. Both answer choice, score, noul, classify and route questions. bosun is licensed apache-2.0; solar-decide, proprietary.
Which is more accurate, bosun or solar-decide?
Only bosun publishes an accuracy figure (84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)); solar-decide does not, so there is no comparison to make without your own test.
Which is cheaper, bosun or solar-decide?
bosun: Free (open weights). solar-decide: $0.1 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run bosun or solar-decide locally?
bosun yes — systemone pull hanno-labs/bosun downloads its weights. The other is only served as a hosted API.
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
